Excited to see this out! This project includes some of my earliest PhD experiments and findings with participant T12. Huge congrats to @BenyaminAK_BCI and the rest of the team for building on it and getting it across the finish line!

Massive shoutout to the participants T12,T15,T16,T17, my advisors and all the coauthors integral to this work! @JaimieHenderson @ShaulDr @BrainGateTeam @neuroleigh @seanyoon777 @foram_kamdar @chethan @NS_Card @ca_rrina @SergeyStavisky @DrDavidBrandman and many more!

Our findings show that inner speech could be a powerful new modality for BCIs—but also highlight the importance of privacy & agency. By decoding imagined sentences and creating safeguards, we aim to move toward communication neuroprosthetics that are empowering in all aspects.

To address this, we propose two simple yet effective strategies—a new way to train an attempted speech BCI to ignore inner speech, and a password-protection system that prevents inner speech from being decoded unless the user first imagines the password

But there’s a challenge: if inner speech lives in motor cortex, could a BCI accidentally decode something a user only intended to think, not say? In controlled cognitive tasks, like silently counting shapes in a grid, we found BCIs could indeed pick up number words.

Inner speech was highly correlated with attempted speech. But we discovered a unique “motor-intent” dimension that separates them—with ALS who was completely anarthric—suggesting attempted speech remains a viable BCI driver even in near locked-in states.

For people who’ve lost the ability to speak, a BCI decoding inner speech might be more comfortable by bypassing physical effort while still enabling fluent communication. Here T16 uses an attempted speech BCI :speaking:

We investigated inner speech in the motor cortex—finding a robust representation that enabled real-time decoding of imagined sentences with error rates as low as 14% for a 50-word and 26% for a 125,000-word vocabulary

Excited to share our new study on inner speech out now in @CellPressNews! W/ @benyameister (co-lead) @WillettNeuro (senior) doi.org/10.1016/j.cell.2025.…

It’s been a fun journey putting this together with our participants and our collaborators. Thanks to all contributors including my co-lead author @benyameister and mentors @WillettNeuro @ShaulDr and @JaimieHenderson !

We’re also presenting this work at #sfn2024 today (poster H19) and at a Minisymposium organized by @SergeyStavisky Monday Oct 7 2-4:30pm. Come talk to us to learn more!

In sum, despite highly overlapping representations across many verbal behaviors our work suggests there is a path forward to safely preserve mental privacy. We look forward to contributing to the conversation around responsible neurotechnology development!

Indeed, typical speech decoders inadvertently decode inner speech with very high frequency (blue). However, an “imagery silenced” decoder training strategy was able to prevent this from happening with high accuracy (gray).

Word representations were highly correlated between overt speech (solid) and inner speech (dashed), and even listening and reading! This raises a risk of unintentional decoding; however, behaviors were still separable in neural state space along an “overtness” axis.

We show that internally spoken sentences can be decoded in real-time with accuracies between 14-33% error rate for a 50 word vocabulary. This suggests that verbal thought is strongly encoded in areas of motor cortex typically targeted for speech BCIs.